Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations it discloses the key behavior an agent cannot get elsewhere: cost of 2 credits per account per week, charged at the first check each week, persistence until paused/stopped, and that re-running with identical input is a no-op. This matches the destructiveHint/idempotentHint flags without contradicting them and adds material operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action and cost, and every clause carries information about signals or billing. The enumeration of signal types is long and delivered as one dense paragraph, and lines like "Watched accounts keep their rules" are vague filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested, multi-object payload this covers the signal model well, but gaps remain: the `instructions` parameter is undocumented, the required contact_signals array behavior under contact_scope=none is unaddressed, and with no output schema there is no hint about what the call returns (e.g., watch IDs or statuses).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description carries the burden and does explain the signal taxonomy and the optional knobs (departments, seniorities, keywords, minimum_amount_usd, contact_scope all + job_change/title_change). However it never mentions the `instructions` field, the 1-100 card_ids bounds, or that contact_signals must be supplied even when contact_scope is "none".

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Starts watching pipeline accounts ... for the same signals" gives a specific verb (starts watching) and resource (pipeline accounts), and ties the input source to getPipeline. It is clearly distinguishable from getAccountWatch and setWatchStatus by implication, though the phrase "for the same signals" is slightly opaque on first read.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It tells the agent where the required card_ids come from ("from getPipeline (find one with company)") and mentions the lifecycle end state ("until it is paused or stopped"), implicitly pointing at setWatchStatus. It stops short of naming alternatives explicitly or warning when not to watch (e.g., accounts already watched).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.